diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 47c6cd6e5487b8..c8f7b5c35a3816 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -5033,60 +5033,56 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
   MVT IndexContainerVT =
       ContainerVT.changeVectorElementType(IndexVT.getScalarType());
 
-  // Base case for the recursion just below - handle the worst case
-  // single source permutation.  Note that all the splat variants
-  // are handled above.
-  if (V2.isUndef()) {
+  SDValue Gather;
+  // TODO: This doesn't trigger for i64 vectors on RV32, since there we
+  // encounter a bitcasted BUILD_VECTOR with low/high i32 values.
+  if (SDValue SplatValue = DAG.getSplatValue(V1, /*LegalTypes*/ true)) {
+    Gather = lowerScalarSplat(SDValue(), SplatValue, VL, ContainerVT, DL, DAG,
+                              Subtarget);
+  } else {
     V1 = convertToScalableVector(ContainerVT, V1, DAG, Subtarget);
-    SDValue LHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesLHS);
-    LHSIndices = convertToScalableVector(IndexContainerVT, LHSIndices, DAG,
-                                         Subtarget);
-    SDValue Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V1, LHSIndices,
-                                 DAG.getUNDEF(ContainerVT), TrueMask, VL);
-    return convertFromScalableVector(VT, Gather, DAG, Subtarget);
-  }
-
-  // Translate the gather index we computed above (and possibly swapped)
-  // back to a shuffle mask.  This step should disappear once we complete
-  // the migration to recursive design.
-  SmallVector<int> ShuffleMaskLHS;
-  ShuffleMaskLHS.reserve(GatherIndicesLHS.size());
-  for (SDValue GatherIndex : GatherIndicesLHS) {
-    if (GatherIndex.isUndef()) {
-      ShuffleMaskLHS.push_back(-1);
-      continue;
+    // If only one index is used, we can use a "splat" vrgather.
+    // TODO: We can splat the most-common index and fix-up any stragglers, if
+    // that's beneficial.
+    if (LHSIndexCounts.size() == 1) {
+      int SplatIndex = LHSIndexCounts.begin()->getFirst();
+      Gather = DAG.getNode(GatherVXOpc, DL, ContainerVT, V1,
+                           DAG.getConstant(SplatIndex, DL, XLenVT),
+                           DAG.getUNDEF(ContainerVT), TrueMask, VL);
+    } else {
+      SDValue LHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesLHS);
+      LHSIndices =
+          convertToScalableVector(IndexContainerVT, LHSIndices, DAG, Subtarget);
+
+      Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V1, LHSIndices,
+                           DAG.getUNDEF(ContainerVT), TrueMask, VL);
     }
-    auto *IdxC = cast<ConstantSDNode>(GatherIndex);
-    ShuffleMaskLHS.push_back(IdxC->getZExtValue());
   }
 
-  // Recursively invoke lowering for the LHS as if there were no RHS.
-  // This allows us to leverage all of our single source permute tricks.
-  SDValue Gather =
-    DAG.getVectorShuffle(VT, DL, V1, DAG.getUNDEF(VT), ShuffleMaskLHS);
-  Gather = convertToScalableVector(ContainerVT, Gather, DAG, Subtarget);
+  // If a second vector operand is used by this shuffle, blend it in with an
+  // additional vrgather.
+  if (!V2.isUndef()) {
+    V2 = convertToScalableVector(ContainerVT, V2, DAG, Subtarget);
 
-  // Blend in second vector source with an additional vrgather.
-  V2 = convertToScalableVector(ContainerVT, V2, DAG, Subtarget);
+    MVT MaskContainerVT = ContainerVT.changeVectorElementType(MVT::i1);
+    SelectMask =
+        convertToScalableVector(MaskContainerVT, SelectMask, DAG, Subtarget);
 
-  MVT MaskContainerVT = ContainerVT.changeVectorElementType(MVT::i1);
-  SelectMask =
-    convertToScalableVector(MaskContainerVT, SelectMask, DAG, Subtarget);
-
-  // If only one index is used, we can use a "splat" vrgather.
-  // TODO: We can splat the most-common index and fix-up any stragglers, if
-  // that's beneficial.
-  if (RHSIndexCounts.size() == 1) {
-    int SplatIndex = RHSIndexCounts.begin()->getFirst();
-    Gather = DAG.getNode(GatherVXOpc, DL, ContainerVT, V2,
-                         DAG.getConstant(SplatIndex, DL, XLenVT), Gather,
-                         SelectMask, VL);
-  } else {
-    SDValue RHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesRHS);
-    RHSIndices =
-      convertToScalableVector(IndexContainerVT, RHSIndices, DAG, Subtarget);
-    Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V2, RHSIndices, Gather,
-                         SelectMask, VL);
+    // If only one index is used, we can use a "splat" vrgather.
+    // TODO: We can splat the most-common index and fix-up any stragglers, if
+    // that's beneficial.
+    if (RHSIndexCounts.size() == 1) {
+      int SplatIndex = RHSIndexCounts.begin()->getFirst();
+      Gather = DAG.getNode(GatherVXOpc, DL, ContainerVT, V2,
+                           DAG.getConstant(SplatIndex, DL, XLenVT), Gather,
+                           SelectMask, VL);
+    } else {
+      SDValue RHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesRHS);
+      RHSIndices =
+          convertToScalableVector(IndexContainerVT, RHSIndices, DAG, Subtarget);
+      Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V2, RHSIndices, Gather,
+                           SelectMask, VL);
+    }
   }
 
   return convertFromScalableVector(VT, Gather, DAG, Subtarget);
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
index dab530751ef96b..799aebcaa63026 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
@@ -238,26 +238,39 @@ define <64 x half> @interleave_v32f16(<32 x half> %x, <32 x half> %y) {
 define <64 x float> @interleave_v32f32(<32 x float> %x, <32 x float> %y) {
 ; V128-LABEL: interleave_v32f32:
 ; V128:       # %bb.0:
-; V128-NEXT:    vsetivli zero, 16, e32, m8, ta, ma
-; V128-NEXT:    vslidedown.vi v0, v8, 16
-; V128-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
-; V128-NEXT:    vwaddu.vv v24, v0, v8
-; V128-NEXT:    li a0, -1
-; V128-NEXT:    vwmaccu.vx v24, a0, v8
-; V128-NEXT:    lui a1, %hi(.LCPI10_0)
-; V128-NEXT:    addi a1, a1, %lo(.LCPI10_0)
-; V128-NEXT:    li a2, 32
-; V128-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
-; V128-NEXT:    vle16.v v12, (a1)
-; V128-NEXT:    lui a1, 699051
-; V128-NEXT:    addi a1, a1, -1366
-; V128-NEXT:    vmv.s.x v0, a1
+; V128-NEXT:    addi sp, sp, -16
+; V128-NEXT:    .cfi_def_cfa_offset 16
+; V128-NEXT:    csrr a0, vlenb
+; V128-NEXT:    slli a0, a0, 2
+; V128-NEXT:    sub sp, sp, a0
+; V128-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x04, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 4 * vlenb
+; V128-NEXT:    lui a0, %hi(.LCPI10_0)
+; V128-NEXT:    addi a0, a0, %lo(.LCPI10_0)
+; V128-NEXT:    li a1, 32
+; V128-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; V128-NEXT:    vle16.v v4, (a0)
+; V128-NEXT:    lui a0, %hi(.LCPI10_1)
+; V128-NEXT:    addi a0, a0, %lo(.LCPI10_1)
+; V128-NEXT:    vle16.v v24, (a0)
+; V128-NEXT:    addi a0, sp, 16
+; V128-NEXT:    vs4r.v v24, (a0) # Unknown-size Folded Spill
+; V128-NEXT:    lui a0, 699051
+; V128-NEXT:    addi a0, a0, -1366
+; V128-NEXT:    vmv.s.x v0, a0
+; V128-NEXT:    vrgatherei16.vv v24, v8, v4
+; V128-NEXT:    addi a0, sp, 16
+; V128-NEXT:    vl4r.v v12, (a0) # Unknown-size Folded Reload
 ; V128-NEXT:    vrgatherei16.vv v24, v16, v12, v0.t
 ; V128-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
 ; V128-NEXT:    vwaddu.vv v0, v8, v16
+; V128-NEXT:    li a0, -1
 ; V128-NEXT:    vwmaccu.vx v0, a0, v16
 ; V128-NEXT:    vmv8r.v v8, v0
 ; V128-NEXT:    vmv8r.v v16, v24
+; V128-NEXT:    csrr a0, vlenb
+; V128-NEXT:    slli a0, a0, 2
+; V128-NEXT:    add sp, sp, a0
+; V128-NEXT:    addi sp, sp, 16
 ; V128-NEXT:    ret
 ;
 ; V512-LABEL: interleave_v32f32:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
index 9e21cc9e3d624a..e1bd16649eede7 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
@@ -188,30 +188,24 @@ define <4 x i32> @interleave_v4i32_offset_2(<4 x i32> %x, <4 x i32> %y) {
 define <4 x i32> @interleave_v4i32_offset_1(<4 x i32> %x, <4 x i32> %y) {
 ; V128-LABEL: interleave_v4i32_offset_1:
 ; V128:       # %bb.0:
-; V128-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; V128-NEXT:    vwaddu.vv v10, v8, v8
-; V128-NEXT:    li a0, -1
-; V128-NEXT:    vwmaccu.vx v10, a0, v8
 ; V128-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; V128-NEXT:    vid.v v8
-; V128-NEXT:    vsrl.vi v8, v8, 1
+; V128-NEXT:    vid.v v10
+; V128-NEXT:    vsrl.vi v11, v10, 1
+; V128-NEXT:    vrgather.vv v10, v8, v11
 ; V128-NEXT:    vmv.v.i v0, 10
-; V128-NEXT:    vadd.vi v8, v8, 1
+; V128-NEXT:    vadd.vi v8, v11, 1
 ; V128-NEXT:    vrgather.vv v10, v9, v8, v0.t
 ; V128-NEXT:    vmv.v.v v8, v10
 ; V128-NEXT:    ret
 ;
 ; V512-LABEL: interleave_v4i32_offset_1:
 ; V512:       # %bb.0:
-; V512-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; V512-NEXT:    vwaddu.vv v10, v8, v8
-; V512-NEXT:    li a0, -1
-; V512-NEXT:    vwmaccu.vx v10, a0, v8
 ; V512-NEXT:    vsetivli zero, 4, e32, mf2, ta, mu
-; V512-NEXT:    vid.v v8
-; V512-NEXT:    vsrl.vi v8, v8, 1
+; V512-NEXT:    vid.v v10
+; V512-NEXT:    vsrl.vi v11, v10, 1
+; V512-NEXT:    vrgather.vv v10, v8, v11
 ; V512-NEXT:    vmv.v.i v0, 10
-; V512-NEXT:    vadd.vi v8, v8, 1
+; V512-NEXT:    vadd.vi v8, v11, 1
 ; V512-NEXT:    vrgather.vv v10, v9, v8, v0.t
 ; V512-NEXT:    vmv1r.v v8, v10
 ; V512-NEXT:    ret
@@ -403,26 +397,39 @@ define <64 x i16> @interleave_v32i16(<32 x i16> %x, <32 x i16> %y) {
 define <64 x i32> @interleave_v32i32(<32 x i32> %x, <32 x i32> %y) {
 ; V128-LABEL: interleave_v32i32:
 ; V128:       # %bb.0:
-; V128-NEXT:    vsetivli zero, 16, e32, m8, ta, ma
-; V128-NEXT:    vslidedown.vi v0, v8, 16
-; V128-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
-; V128-NEXT:    vwaddu.vv v24, v0, v8
-; V128-NEXT:    li a0, -1
-; V128-NEXT:    vwmaccu.vx v24, a0, v8
-; V128-NEXT:    lui a1, %hi(.LCPI17_0)
-; V128-NEXT:    addi a1, a1, %lo(.LCPI17_0)
-; V128-NEXT:    li a2, 32
-; V128-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
-; V128-NEXT:    vle16.v v12, (a1)
-; V128-NEXT:    lui a1, 699051
-; V128-NEXT:    addi a1, a1, -1366
-; V128-NEXT:    vmv.s.x v0, a1
+; V128-NEXT:    addi sp, sp, -16
+; V128-NEXT:    .cfi_def_cfa_offset 16
+; V128-NEXT:    csrr a0, vlenb
+; V128-NEXT:    slli a0, a0, 2
+; V128-NEXT:    sub sp, sp, a0
+; V128-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x04, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 4 * vlenb
+; V128-NEXT:    lui a0, %hi(.LCPI17_0)
+; V128-NEXT:    addi a0, a0, %lo(.LCPI17_0)
+; V128-NEXT:    li a1, 32
+; V128-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; V128-NEXT:    vle16.v v4, (a0)
+; V128-NEXT:    lui a0, %hi(.LCPI17_1)
+; V128-NEXT:    addi a0, a0, %lo(.LCPI17_1)
+; V128-NEXT:    vle16.v v24, (a0)
+; V128-NEXT:    addi a0, sp, 16
+; V128-NEXT:    vs4r.v v24, (a0) # Unknown-size Folded Spill
+; V128-NEXT:    lui a0, 699051
+; V128-NEXT:    addi a0, a0, -1366
+; V128-NEXT:    vmv.s.x v0, a0
+; V128-NEXT:    vrgatherei16.vv v24, v8, v4
+; V128-NEXT:    addi a0, sp, 16
+; V128-NEXT:    vl4r.v v12, (a0) # Unknown-size Folded Reload
 ; V128-NEXT:    vrgatherei16.vv v24, v16, v12, v0.t
 ; V128-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
 ; V128-NEXT:    vwaddu.vv v0, v8, v16
+; V128-NEXT:    li a0, -1
 ; V128-NEXT:    vwmaccu.vx v0, a0, v16
 ; V128-NEXT:    vmv8r.v v8, v0
 ; V128-NEXT:    vmv8r.v v16, v24
+; V128-NEXT:    csrr a0, vlenb
+; V128-NEXT:    slli a0, a0, 2
+; V128-NEXT:    add sp, sp, a0
+; V128-NEXT:    addi sp, sp, 16
 ; V128-NEXT:    ret
 ;
 ; V512-LABEL: interleave_v32i32:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
index a26a87a1f3c139..a56a81f5f793bc 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
@@ -612,11 +612,13 @@ define <8 x i8> @concat_4xi8_start_undef_at_start(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: concat_4xi8_start_undef_at_start:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 224
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vadd.vi v10, v10, -4
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -4
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 9, i32 10, i32 11>
   ret <8 x i8> %res
@@ -626,11 +628,13 @@ define <8 x i8> @merge_start_into_end_non_contiguous(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: merge_start_into_end_non_contiguous:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 144
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vadd.vi v10, v10, -4
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -4
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 5, i32 6, i32 11>
   ret <8 x i8> %res
@@ -671,11 +675,13 @@ define <8 x i8> @merge_slidedown(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: merge_slidedown:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    li a0, 195
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 14, i32 15>
   ret <8 x i8> %res
@@ -686,12 +692,14 @@ define <8 x i8> @merge_non_contiguous_slideup_slidedown(<8 x i8> %v, <8 x i8> %w
 ; CHECK-LABEL: merge_non_contiguous_slideup_slidedown:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 2
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
 ; CHECK-NEXT:    li a0, 234
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vslidedown.vi v8, v8, 2
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 2, i32 8, i32 4, i32 10, i32 6, i32 12, i32 13, i32 14>
   ret <8 x i8> %res
@@ -702,13 +710,16 @@ define <8 x i8> @unmergable(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: unmergable:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vadd.vi v11, v10, 2
 ; CHECK-NEXT:    lui a0, %hi(.LCPI46_0)
 ; CHECK-NEXT:    addi a0, a0, %lo(.LCPI46_0)
-; CHECK-NEXT:    vle8.v v10, (a0)
+; CHECK-NEXT:    vle8.v v12, (a0)
 ; CHECK-NEXT:    li a0, 234
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vslidedown.vi v8, v8, 2
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
+; CHECK-NEXT:    vrgather.vv v10, v9, v12, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 2, i32 9, i32 4, i32 11, i32 6, i32 13, i32 8, i32 15>
   ret <8 x i8> %res
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
index f889041647b235..eeb8e517d01d2d 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
@@ -8,51 +8,23 @@
 
 ; FIXME: This should be widened to a vlseg2 of <4 x i32> with VL set to 3
 define {<3 x i32>, <3 x i32>} @load_factor2_v3(ptr %ptr) {
-; RV32-LABEL: load_factor2_v3:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli zero, 6, e32, m2, ta, ma
-; RV32-NEXT:    vle32.v v10, (a0)
-; RV32-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV32-NEXT:    vslidedown.vi v9, v10, 2
-; RV32-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; RV32-NEXT:    vwaddu.vv v8, v10, v9
-; RV32-NEXT:    li a0, -1
-; RV32-NEXT:    vwmaccu.vx v8, a0, v9
-; RV32-NEXT:    vmv.v.i v0, 4
-; RV32-NEXT:    vsetivli zero, 4, e32, m2, ta, ma
-; RV32-NEXT:    vslidedown.vi v12, v10, 4
-; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; RV32-NEXT:    vrgather.vi v8, v12, 0, v0.t
-; RV32-NEXT:    vid.v v9
-; RV32-NEXT:    vadd.vv v9, v9, v9
-; RV32-NEXT:    vadd.vi v11, v9, 1
-; RV32-NEXT:    vrgather.vv v9, v10, v11
-; RV32-NEXT:    vrgather.vi v9, v12, 1, v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: load_factor2_v3:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli zero, 6, e32, m2, ta, ma
-; RV64-NEXT:    vle32.v v10, (a0)
-; RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; RV64-NEXT:    vid.v v8
-; RV64-NEXT:    vadd.vv v8, v8, v8
-; RV64-NEXT:    vadd.vi v8, v8, 1
-; RV64-NEXT:    vrgather.vv v9, v10, v8
-; RV64-NEXT:    vmv.v.i v0, 4
-; RV64-NEXT:    vsetivli zero, 4, e32, m2, ta, ma
-; RV64-NEXT:    vslidedown.vi v12, v10, 4
-; RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; RV64-NEXT:    vrgather.vi v9, v12, 1, v0.t
-; RV64-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV64-NEXT:    vslidedown.vi v11, v10, 2
-; RV64-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; RV64-NEXT:    vwaddu.vv v8, v10, v11
-; RV64-NEXT:    li a0, -1
-; RV64-NEXT:    vwmaccu.vx v8, a0, v11
-; RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; RV64-NEXT:    vrgather.vi v8, v12, 0, v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: load_factor2_v3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 6, e32, m2, ta, ma
+; CHECK-NEXT:    vle32.v v10, (a0)
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vv v9, v8, v8
+; CHECK-NEXT:    vrgather.vv v8, v10, v9
+; CHECK-NEXT:    vmv.v.i v0, 4
+; CHECK-NEXT:    vsetivli zero, 4, e32, m2, ta, ma
+; CHECK-NEXT:    vslidedown.vi v12, v10, 4
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vrgather.vi v8, v12, 0, v0.t
+; CHECK-NEXT:    vadd.vi v11, v9, 1
+; CHECK-NEXT:    vrgather.vv v9, v10, v11
+; CHECK-NEXT:    vrgather.vi v9, v12, 1, v0.t
+; CHECK-NEXT:    ret
   %interleaved.vec = load <6 x i32>, ptr %ptr
   %v0 = shufflevector <6 x i32> %interleaved.vec, <6 x i32> poison, <3 x i32> <i32 0, i32 2, i32 4>
   %v1 = shufflevector <6 x i32> %interleaved.vec, <6 x i32> poison, <3 x i32> <i32 1, i32 3, i32 5>
@@ -159,142 +131,163 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    addi sp, sp, -16
 ; RV32-NEXT:    .cfi_def_cfa_offset 16
 ; RV32-NEXT:    csrr a2, vlenb
-; RV32-NEXT:    li a3, 58
+; RV32-NEXT:    li a3, 62
 ; RV32-NEXT:    mul a2, a2, a3
 ; RV32-NEXT:    sub sp, sp, a2
-; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x3a, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 58 * vlenb
-; RV32-NEXT:    addi a3, a1, 256
+; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x3e, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 62 * vlenb
+; RV32-NEXT:    addi a3, a1, 128
+; RV32-NEXT:    addi a4, a1, 256
 ; RV32-NEXT:    li a2, 32
 ; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
-; RV32-NEXT:    vle32.v v8, (a3)
-; RV32-NEXT:    csrr a3, vlenb
-; RV32-NEXT:    li a4, 25
-; RV32-NEXT:    mul a3, a3, a4
-; RV32-NEXT:    add a3, sp, a3
-; RV32-NEXT:    addi a3, a3, 16
-; RV32-NEXT:    vs8r.v v8, (a3) # Unknown-size Folded Spill
-; RV32-NEXT:    addi a3, a1, 128
-; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
-; RV32-NEXT:    vslideup.vi v16, v8, 4
+; RV32-NEXT:    vle32.v v16, (a4)
 ; RV32-NEXT:    csrr a4, vlenb
-; RV32-NEXT:    li a5, 12
+; RV32-NEXT:    li a5, 29
 ; RV32-NEXT:    mul a4, a4, a5
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
-; RV32-NEXT:    vs4r.v v16, (a4) # Unknown-size Folded Spill
-; RV32-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
-; RV32-NEXT:    vid.v v20
-; RV32-NEXT:    vadd.vi v4, v20, -10
-; RV32-NEXT:    vmv.v.v v2, v20
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; RV32-NEXT:    vid.v v10
 ; RV32-NEXT:    csrr a4, vlenb
-; RV32-NEXT:    slli a5, a4, 4
+; RV32-NEXT:    slli a5, a4, 3
 ; RV32-NEXT:    add a4, a5, a4
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
-; RV32-NEXT:    vs2r.v v20, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vs2r.v v10, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vadd.vi v8, v10, -4
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 13
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs2r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
+; RV32-NEXT:    vrgatherei16.vv v12, v16, v8
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 21
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs4r.v v12, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; RV32-NEXT:    vadd.vi v8, v10, -10
 ; RV32-NEXT:    lui a4, 12
-; RV32-NEXT:    vmv.s.x v1, a4
-; RV32-NEXT:    vsetivli zero, 16, e32, m8, ta, ma
-; RV32-NEXT:    vslidedown.vi v8, v8, 16
+; RV32-NEXT:    vmv.s.x v0, a4
 ; RV32-NEXT:    csrr a4, vlenb
-; RV32-NEXT:    slli a5, a4, 5
-; RV32-NEXT:    add a4, a5, a4
+; RV32-NEXT:    slli a4, a4, 3
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
-; RV32-NEXT:    vs8r.v v8, (a4) # Unknown-size Folded Spill
-; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
-; RV32-NEXT:    vmv1r.v v0, v1
+; RV32-NEXT:    vs1r.v v0, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetivli zero, 16, e32, m8, ta, ma
+; RV32-NEXT:    vslidedown.vi v16, v16, 16
 ; RV32-NEXT:    csrr a4, vlenb
-; RV32-NEXT:    slli a4, a4, 4
+; RV32-NEXT:    li a5, 45
+; RV32-NEXT:    mul a4, a4, a5
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
-; RV32-NEXT:    vs1r.v v1, (a4) # Unknown-size Folded Spill
-; RV32-NEXT:    vrgatherei16.vv v16, v8, v4, v0.t
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; RV32-NEXT:    vrgatherei16.vv v12, v16, v8, v0.t
 ; RV32-NEXT:    csrr a4, vlenb
-; RV32-NEXT:    li a5, 21
+; RV32-NEXT:    li a5, 25
 ; RV32-NEXT:    mul a4, a4, a5
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
-; RV32-NEXT:    vs4r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vs4r.v v12, (a4) # Unknown-size Folded Spill
 ; RV32-NEXT:    lui a4, %hi(.LCPI6_0)
 ; RV32-NEXT:    addi a4, a4, %lo(.LCPI6_0)
 ; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
+; RV32-NEXT:    lui a5, %hi(.LCPI6_1)
+; RV32-NEXT:    addi a5, a5, %lo(.LCPI6_1)
+; RV32-NEXT:    lui a6, 1
 ; RV32-NEXT:    vle16.v v8, (a4)
+; RV32-NEXT:    addi a4, sp, 16
+; RV32-NEXT:    vs4r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vle16.v v8, (a5)
 ; RV32-NEXT:    csrr a4, vlenb
 ; RV32-NEXT:    slli a4, a4, 2
 ; RV32-NEXT:    add a4, sp, a4
 ; RV32-NEXT:    addi a4, a4, 16
 ; RV32-NEXT:    vs4r.v v8, (a4) # Unknown-size Folded Spill
-; RV32-NEXT:    lui a4, %hi(.LCPI6_1)
-; RV32-NEXT:    addi a4, a4, %lo(.LCPI6_1)
-; RV32-NEXT:    lui a5, 1
-; RV32-NEXT:    vle16.v v8, (a4)
-; RV32-NEXT:    addi a4, sp, 16
-; RV32-NEXT:    vs4r.v v8, (a4) # Unknown-size Folded Spill
 ; RV32-NEXT:    vle32.v v16, (a1)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a4, 49
+; RV32-NEXT:    li a4, 37
 ; RV32-NEXT:    mul a1, a1, a4
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    vle32.v v24, (a3)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 41
+; RV32-NEXT:    li a3, 53
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
-; RV32-NEXT:    addi a1, a5, -64
+; RV32-NEXT:    addi a1, a6, -64
 ; RV32-NEXT:    vmv.s.x v0, a1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 3
+; RV32-NEXT:    slli a3, a1, 4
+; RV32-NEXT:    add a1, a3, a1
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs1r.v v0, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    addi a1, sp, 16
+; RV32-NEXT:    vl4r.v v4, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v8, v16, v4
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl4r.v v4, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v16, v4
-; RV32-NEXT:    addi a1, sp, 16
 ; RV32-NEXT:    vl4r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v8, v24, v16, v0.t
 ; RV32-NEXT:    vsetivli zero, 12, e32, m4, tu, ma
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 21
+; RV32-NEXT:    li a3, 25
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl4r.v v12, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vmv.v.v v12, v8
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 21
+; RV32-NEXT:    li a3, 25
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs4r.v v12, (a1) # Unknown-size Folded Spill
-; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 25
+; RV32-NEXT:    slli a3, a1, 3
+; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vl2r.v v10, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vadd.vi v8, v10, -2
+; RV32-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a3, 29
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl8r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vslideup.vi v12, v8, 2
+; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v12, v16, v8
 ; RV32-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
-; RV32-NEXT:    vadd.vi v8, v2, -8
+; RV32-NEXT:    vadd.vi v8, v10, -8
+; RV32-NEXT:    vmv2r.v v30, v10
 ; RV32-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
-; RV32-NEXT:    vmv1r.v v0, v1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 5
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    slli a1, a1, 3
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vl1r.v v28, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vmv1r.v v0, v28
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a3, 45
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v12, v16, v8, v0.t
-; RV32-NEXT:    vmv.v.v v20, v12
+; RV32-NEXT:    vmv.v.v v24, v12
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_2)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_2)
 ; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
@@ -308,165 +301,166 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs4r.v v8, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 49
+; RV32-NEXT:    li a3, 37
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v0, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v8, v0, v16
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 3
+; RV32-NEXT:    slli a3, a1, 4
+; RV32-NEXT:    add a1, a3, a1
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 41
+; RV32-NEXT:    li a3, 53
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl4r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v24, v16, v0.t
+; RV32-NEXT:    vl4r.v v4, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v8, v16, v4, v0.t
 ; RV32-NEXT:    vsetivli zero, 12, e32, m4, tu, ma
-; RV32-NEXT:    vmv.v.v v20, v8
+; RV32-NEXT:    vmv.v.v v24, v8
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 3
+; RV32-NEXT:    slli a3, a1, 4
+; RV32-NEXT:    add a1, a3, a1
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vs4r.v v20, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    vs4r.v v24, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_4)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_4)
 ; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
 ; RV32-NEXT:    vle16.v v8, (a1)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 25
+; RV32-NEXT:    li a3, 29
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v24, v16, v8
+; RV32-NEXT:    vrgatherei16.vv v4, v16, v8
 ; RV32-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; RV32-NEXT:    vadd.vi v8, v30, -6
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 4
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    slli a1, a1, 2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl2r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vadd.vi v8, v8, -6
+; RV32-NEXT:    vs2r.v v8, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
+; RV32-NEXT:    vmv1r.v v0, v28
+; RV32-NEXT:    vmv1r.v v2, v28
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 4
-; RV32-NEXT:    add a1, sp, a1
-; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 5
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    li a3, 45
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v24, v16, v8, v0.t
+; RV32-NEXT:    vrgatherei16.vv v4, v16, v8, v0.t
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_5)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_5)
 ; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
 ; RV32-NEXT:    lui a3, %hi(.LCPI6_6)
 ; RV32-NEXT:    addi a3, a3, %lo(.LCPI6_6)
-; RV32-NEXT:    vle16.v v16, (a1)
-; RV32-NEXT:    vle16.v v28, (a3)
+; RV32-NEXT:    vle16.v v20, (a1)
+; RV32-NEXT:    vle16.v v8, (a3)
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    slli a3, a1, 3
+; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vs4r.v v8, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    li a1, 960
-; RV32-NEXT:    vmv.s.x v20, a1
-; RV32-NEXT:    addi a1, sp, 16
-; RV32-NEXT:    vs1r.v v20, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    vmv.s.x v1, a1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 49
+; RV32-NEXT:    li a3, 37
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v0, v16
-; RV32-NEXT:    vmv1r.v v0, v20
+; RV32-NEXT:    vl8r.v v8, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v24, v8, v20
+; RV32-NEXT:    vmv1r.v v0, v1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 41
+; RV32-NEXT:    li a3, 53
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v16, v28, v0.t
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    slli a3, a1, 3
+; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vl4r.v v8, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v24, v16, v8, v0.t
 ; RV32-NEXT:    vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT:    vmv.v.v v24, v8
+; RV32-NEXT:    vmv.v.v v4, v24
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 2
+; RV32-NEXT:    slli a3, a1, 3
+; RV32-NEXT:    add a1, a3, a1
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vs4r.v v24, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    vs4r.v v4, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_7)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_7)
-; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
 ; RV32-NEXT:    vle16.v v8, (a1)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 25
+; RV32-NEXT:    li a3, 29
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v12, v16, v8
-; RV32-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; RV32-NEXT:    vmv1r.v v0, v2
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 4
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    li a3, 13
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl2r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vadd.vi v8, v8, -4
-; RV32-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 4
-; RV32-NEXT:    add a1, sp, a1
-; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 5
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    li a3, 45
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v12, v16, v8, v0.t
-; RV32-NEXT:    vmv.v.v v24, v12
+; RV32-NEXT:    vmv.v.v v4, v12
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_8)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_8)
 ; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
 ; RV32-NEXT:    lui a3, %hi(.LCPI6_9)
 ; RV32-NEXT:    addi a3, a3, %lo(.LCPI6_9)
 ; RV32-NEXT:    vle16.v v16, (a1)
-; RV32-NEXT:    vle16.v v28, (a3)
+; RV32-NEXT:    vle16.v v20, (a3)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 49
+; RV32-NEXT:    li a3, 37
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v0, v16
-; RV32-NEXT:    addi a1, sp, 16
-; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v8, v24, v16
+; RV32-NEXT:    vmv1r.v v0, v1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 41
+; RV32-NEXT:    li a3, 53
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vrgatherei16.vv v8, v16, v28, v0.t
+; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v8, v24, v20, v0.t
 ; RV32-NEXT:    vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT:    vmv.v.v v24, v8
+; RV32-NEXT:    vmv.v.v v4, v8
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 4
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    li a3, 13
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
-; RV32-NEXT:    vs4r.v v24, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    vs4r.v v4, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
 ; RV32-NEXT:    lui a1, %hi(.LCPI6_10)
 ; RV32-NEXT:    addi a1, a1, %lo(.LCPI6_10)
@@ -474,20 +468,25 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    lui a1, 15
 ; RV32-NEXT:    vmv.s.x v0, a1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 4
+; RV32-NEXT:    slli a1, a1, 3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs1r.v v0, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 25
+; RV32-NEXT:    li a3, 29
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT:    vslideup.vi v20, v16, 6
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 5
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    slli a1, a1, 2
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vl2r.v v10, (a1) # Unknown-size Folded Reload
+; RV32-NEXT:    vrgatherei16.vv v20, v16, v10
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a3, 45
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
@@ -502,13 +501,13 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    li a1, 1008
 ; RV32-NEXT:    vmv.s.x v28, a1
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 25
+; RV32-NEXT:    li a3, 29
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs1r.v v28, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 49
+; RV32-NEXT:    li a3, 37
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
@@ -516,7 +515,7 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    vrgatherei16.vv v8, v0, v24
 ; RV32-NEXT:    vmv1r.v v0, v28
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 41
+; RV32-NEXT:    li a3, 53
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
@@ -529,19 +528,19 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
 ; RV32-NEXT:    vle16.v v8, (a1)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a1, a1, 4
+; RV32-NEXT:    slli a1, a1, 3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a3, 12
+; RV32-NEXT:    li a3, 21
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl4r.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a3, a1, 5
-; RV32-NEXT:    add a1, a3, a1
+; RV32-NEXT:    li a3, 45
+; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
@@ -554,33 +553,33 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    vle16.v v24, (a1)
 ; RV32-NEXT:    vle16.v v8, (a2)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a2, a1, 5
-; RV32-NEXT:    add a1, a2, a1
+; RV32-NEXT:    li a2, 45
+; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vs4r.v v8, (a1) # Unknown-size Folded Spill
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a2, 49
+; RV32-NEXT:    li a2, 37
 ; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v0, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vrgatherei16.vv v8, v0, v24
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a2, 25
+; RV32-NEXT:    li a2, 29
 ; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl1r.v v0, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a2, 41
+; RV32-NEXT:    li a2, 53
 ; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl8r.v v24, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    slli a2, a1, 5
-; RV32-NEXT:    add a1, a2, a1
+; RV32-NEXT:    li a2, 45
+; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl4r.v v4, (a1) # Unknown-size Folded Reload
@@ -594,35 +593,37 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
 ; RV32-NEXT:    vse32.v v20, (a1)
 ; RV32-NEXT:    addi a1, a0, 192
 ; RV32-NEXT:    csrr a2, vlenb
-; RV32-NEXT:    slli a3, a2, 4
-; RV32-NEXT:    add a2, a3, a2
+; RV32-NEXT:    li a3, 13
+; RV32-NEXT:    mul a2, a2, a3
 ; RV32-NEXT:    add a2, sp, a2
 ; RV32-NEXT:    addi a2, a2, 16
 ; RV32-NEXT:    vl4r.v v8, (a2) # Unknown-size Folded Reload
 ; RV32-NEXT:    vse32.v v8, (a1)
 ; RV32-NEXT:    addi a1, a0, 128
 ; RV32-NEXT:    csrr a2, vlenb
-; RV32-NEXT:    slli a2, a2, 2
+; RV32-NEXT:    slli a3, a2, 3
+; RV32-NEXT:    add a2, a3, a2
 ; RV32-NEXT:    add a2, sp, a2
 ; RV32-NEXT:    addi a2, a2, 16
 ; RV32-NEXT:    vl4r.v v8, (a2) # Unknown-size Folded Reload
 ; RV32-NEXT:    vse32.v v8, (a1)
 ; RV32-NEXT:    addi a1, a0, 64
 ; RV32-NEXT:    csrr a2, vlenb
-; RV32-NEXT:    slli a2, a2, 3
+; RV32-NEXT:    slli a3, a2, 4
+; RV32-NEXT:    add a2, a3, a2
 ; RV32-NEXT:    add a2, sp, a2
 ; RV32-NEXT:    addi a2, a2, 16
 ; RV32-NEXT:    vl4r.v v8, (a2) # Unknown-size Folded Reload
 ; RV32-NEXT:    vse32.v v8, (a1)
 ; RV32-NEXT:    csrr a1, vlenb
-; RV32-NEXT:    li a2, 21
+; RV32-NEXT:    li a2, 25
 ; RV32-NEXT:    mul a1, a1, a2
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 16
 ; RV32-NEXT:    vl4r.v v8, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    vse32.v v8, (a0)
 ; RV32-NEXT:    csrr a0, vlenb
-; RV32-NEXT:    li a1, 58
+; RV32-NEXT:    li a1, 62
 ; RV32-NEXT:    mul a0, a0, a1
 ; RV32-NEXT:    add sp, sp, a0
 ; RV32-NEXT:    addi sp, sp, 16
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
index a34fa9502d93b3..d0777962a75651 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
@@ -8,11 +8,13 @@ define <8 x i8> @trn1.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
 ; CHECK-LABEL: trn1.v8i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
   ret <8 x i8> %tmp0
@@ -22,11 +24,13 @@ define <8 x i8> @trn2.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
 ; CHECK-LABEL: trn2.v8i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
   ret <8 x i8> %tmp0
@@ -36,14 +40,16 @@ define <16 x i8> @trn1.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
 ; CHECK-LABEL: trn1.v16i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
+; CHECK-NEXT:    vadd.vi v8, v11, -1
 ; CHECK-NEXT:    lui a0, 11
 ; CHECK-NEXT:    addi a0, a0, -1366
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv.s.x v0, a0
 ; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
   ret <16 x i8> %tmp0
@@ -53,14 +59,16 @@ define <16 x i8> @trn2.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
 ; CHECK-LABEL: trn2.v16i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
 ; CHECK-NEXT:    lui a0, 11
 ; CHECK-NEXT:    addi a0, a0, -1366
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
 ; CHECK-NEXT:    vmv.s.x v0, a0
 ; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
   ret <16 x i8> %tmp0
@@ -70,10 +78,12 @@ define <4 x i16> @trn1.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
 ; CHECK-LABEL: trn1.v4i16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x i16> %tmp0
@@ -83,10 +93,12 @@ define <4 x i16> @trn2.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
 ; CHECK-LABEL: trn2.v4i16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   ret <4 x i16> %tmp0
@@ -96,11 +108,13 @@ define <8 x i16> @trn1.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
 ; CHECK-LABEL: trn1.v8i16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
   ret <8 x i16> %tmp0
@@ -110,11 +124,13 @@ define <8 x i16> @trn2.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
 ; CHECK-LABEL: trn2.v8i16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
   ret <8 x i16> %tmp0
@@ -147,10 +163,12 @@ define <4 x i32> @trn1.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: trn1.v4i32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x i32> %tmp0
@@ -160,10 +178,12 @@ define <4 x i32> @trn2.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: trn2.v4i32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   ret <4 x i32> %tmp0
@@ -219,10 +239,12 @@ define <4 x float> @trn1.v4f32(<4 x float> %v0, <4 x float> %v1) {
 ; CHECK-LABEL: trn1.v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x float> %tmp0
@@ -232,10 +254,12 @@ define <4 x float> @trn2.v4f32(<4 x float> %v0, <4 x float> %v1) {
 ; CHECK-LABEL: trn2.v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   ret <4 x float> %tmp0
@@ -268,10 +292,12 @@ define <4 x half> @trn1.v4f16(<4 x half> %v0, <4 x half> %v1) {
 ; CHECK-LABEL: trn1.v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x half> %tmp0
@@ -281,10 +307,12 @@ define <4 x half> @trn2.v4f16(<4 x half> %v0, <4 x half> %v1) {
 ; CHECK-LABEL: trn2.v4f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    vmv.v.i v0, 10
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv1r.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   ret <4 x half> %tmp0
@@ -294,11 +322,13 @@ define <8 x half> @trn1.v8f16(<8 x half> %v0, <8 x half> %v1) {
 ; CHECK-LABEL: trn1.v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT:    vid.v v10
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vrgather.vv v10, v8, v11
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vadd.vi v10, v10, -1
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vadd.vi v8, v11, -1
+; CHECK-NEXT:    vrgather.vv v10, v9, v8, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
   ret <8 x half> %tmp0
@@ -308,11 +338,13 @@ define <8 x half> @trn2.v8f16(<8 x half> %v0, <8 x half> %v1) {
 ; CHECK-LABEL: trn2.v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vid.v v11
+; CHECK-NEXT:    vadd.vi v12, v11, 1
 ; CHECK-NEXT:    li a0, 170
 ; CHECK-NEXT:    vmv.s.x v0, a0
-; CHECK-NEXT:    vid.v v10
-; CHECK-NEXT:    vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    vrgather.vv v10, v8, v12
+; CHECK-NEXT:    vrgather.vv v10, v9, v11, v0.t
+; CHECK-NEXT:    vmv.v.v v8, v10
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
   ret <8 x half> %tmp0